New open-access dataset released for marine engine fault detection

Researchers have released the Marine Engine Fault Dataset, an open-access collection of data from a turbocharged, intercooled three-cylinder marine diesel engine. The dataset includes multi-sensor time-series measurements from the engine operated under both reference and controlled fault conditions. Five distinct anomaly classes were introduced through physical interventions, affecting subsystems like the cooling-water pump, air filter, air cooler, injection valve, and turbine. This dataset is intended to serve as a benchmark for studies in anomaly detection, fault diagnosis, and condition monitoring in maritime machinery. AI

IMPACT Provides a benchmark for anomaly detection and fault diagnosis in maritime machinery, potentially advancing AI applications in industrial maintenance.

RANK_REASON The item describes a new dataset released via arXiv, suitable for research purposes. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• Connected Papers
• DagsHub
• Gotit.pub
• Hugging Face
• Litmaps
• Marine Engine Fault Dataset
• Mohammad Mahdi Abaei
• ScienceCast
• scite Smart Citations

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →